{"id":"https://openalex.org/W7154207919","doi":"https://doi.org/10.48550/arxiv.2604.11001","title":"Flow-Controlled Scheduling for LLM Inference with Provable Stability Guarantees","display_name":"Flow-Controlled Scheduling for LLM Inference with Provable Stability Guarantees","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7154207919","doi":"https://doi.org/10.48550/arxiv.2604.11001"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.11001","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.11001","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.11001","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133557500","display_name":"Zhuolun Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Zhuolun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002422731","display_name":"Junyu Cao","orcid":"https://orcid.org/0000-0001-9235-1411"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Junyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.14810000360012054,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.14810000360012054,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.09130000323057175,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.09000000357627869,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6743999719619751},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6539999842643738},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5856999754905701},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5163999795913696},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.48489999771118164},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.3691999912261963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8442999720573425},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6743999719619751},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6539999842643738},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5856999754905701},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5163999795913696},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.48489999771118164},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4372999966144562},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3398999869823456},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.32280001044273376},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29429998993873596},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2766999900341034},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.2621999979019165},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.11001","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.11001","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.11001","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.11001","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"been":[5],"widely":[6],"adopted":[7],"due":[8],"to":[9,71,124],"their":[10],"great":[11],"performance":[12],"across":[13],"a":[14,83,100],"wide":[15],"range":[16],"of":[17,25,27,33],"applications.":[18],"ChatGPT":[19],"and":[20,30,73,109,135,140,143],"Gemini":[21],"now":[22],"serve":[23],"hundreds":[24],"millions":[26],"active":[28,96],"users":[29],"handle":[31],"billions":[32],"user":[34],"requests":[35],"per":[36],"day,":[37],"which":[38,68,92,114],"puts":[39],"optimizing":[40],"LLM":[41,50],"inference":[42,51],"into":[43],"the":[44,89,95],"spotlight.":[45],"A":[46],"key":[47],"challenge":[48],"in":[49,128],"is":[52],"that":[53,87,103],"decode":[54],"lengths":[55],"are":[56],"unknown.":[57],"The":[58],"memory":[59],"usage":[60],"for":[61],"each":[62],"request":[63,136],"grows":[64],"with":[65],"generated":[66],"tokens,":[67],"may":[69],"lead":[70],"overflow":[72],"cause":[74],"system":[75,106],"instability.":[76],"To":[77],"address":[78],"this":[79],"concern,":[80],"we":[81],"propose":[82],"simple":[84],"flow-control":[85],"framework":[86],"controls":[88],"rate":[90],"at":[91],"prompts":[93],"join":[94],"set.":[97],"We":[98],"derive":[99],"necessary":[101],"condition":[102],"any":[104],"stable":[105,145],"must":[107],"satisfy":[108],"establish":[110],"sufficient":[111],"conditions":[112],"under":[113],"our":[115,130],"algorithm":[116],"provably":[117],"achieves":[118,132],"stability.":[119],"Experiments":[120],"show":[121],"that,":[122],"compared":[123],"commonly":[125],"used":[126],"strategies":[127],"practice,":[129],"approach":[131],"higher":[133],"token":[134],"throughput,":[137],"lower":[138],"average":[139],"tail":[141],"latency,":[142],"more":[144],"KV":[146],"cache":[147],"utilization.":[148]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-15T00:00:00"}